Emotion Recognition with Deep Learning-Based Facial Expressions: Comparative Analysis of Algorithms

Ozhan, Caner (2024) Emotion Recognition with Deep Learning-Based Facial Expressions: Comparative Analysis of Algorithms. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (269kB) | Preview

Abstract

This study investigates facial expression recognition (FER) as a foundational element of emotion recognition systems, which enhance human-machine interactions by enabling devices to interpret and respond to human emotions. Using the FER2013 dataset and Google’s MediaPipe Face Mesh, various machine learning models, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), k-Nearest Neighbors (KNN), Random Forests and Logistic Regression, were applied to assess their effectiveness in classifying facial expressions. Results indicate that CNN and Random Forest models achieved the highest accuracy, around 54% and 53%, respectively, with each model demonstrating unique strengths in emotion recognition tasks. This research highlights the role of preprocessing and class balance adjustments in improving model performance and offers insights into enhancing FER systems for real-world applications.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Anand, Devanshu UNSPECIFIED
Uncontrolled Keywords:	FER (Facial Expression Recognition); Face Mesh; Convolutional Neural Networks (CNNs); Mediapipe; Support Vector Machines (SVM); K-Nearest Neighbors (KNN); Logistic Regression
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science B Philosophy. Psychology. Religion > Psychology > Emotions Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	19 Jun 2025 14:48
Last Modified:	19 Jun 2025 14:48
URI:	https://norma.ncirl.ie/id/eprint/7936

Actions (login required)

View Item